Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2334 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0044. Min Range: -3.0044

Max Act: 3.0044. Min Act: -0.1700

Data Index: 1245517 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9926. Min Act: -0.1700

Data Index: 3609123 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9869. Min Act: -0.1700

Data Index: 8742440 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9864. Min Act: -0.1700

Data Index: 543788 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9674. Min Act: -0.1700

Data Index: 5018781 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9675. Min Act: -0.1700

Data Index: 6096266 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9481. Min Act: -0.1700

Data Index: 2756705 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9545. Min Act: -0.1700

Data Index: 4181399 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9302. Min Act: -0.1700

Data Index: 2150766 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9301. Min Act: -0.1700

Data Index: 8789080 (Open Web Text)

Max Activating Token Index: 650

Text #10

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9256. Min Act: -0.1700

Data Index: 842492 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9572. Min Act: -0.1700

Data Index: 6223453 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8988. Min Act: -0.1700

Data Index: 1141552 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9032. Min Act: -0.1700

Data Index: 6465251 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8911. Min Act: -0.1700

Data Index: 7913459 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8994. Min Act: -0.1700

Data Index: 5902561 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.9140. Min Act: -0.1700

Data Index: 1052665 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8759. Min Act: -0.1700

Data Index: 4807790 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8733. Min Act: -0.1700

Data Index: 2333785 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 3.0044. Min Range: -3.0044

Max Act: 2.8669. Min Act: -0.1700

Data Index: 1890 (Open Web Text)

Max Activating Token Index: 530